Protecting Floating-Point Computation for DNN Binaries with MBA Obfuscation
This submission was made prematurely and has been withdrawn by the authors for substantial revision before further dissemination.
cs.CR↗
arXiv subjects
Zichen Zhao
Publications and source records attributed to Zichen Zhao.
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and iterative global refinement capabilities. Unlike continuous diffusion, where the state space is fixed, DDMs are fundamentally shaped by how the discrete state space is constructed: the tokenization scheme, the vocabulary topology, and domain-specific structural alphabets. This work introduces a unified conceptual framework that views discrete diffusion models through the construction of the underlying discrete state space. Within this framework, existing formulations, including transition-matrix, masking/absorbing-state, and score/ratio-based approaches, emerge as different instantiations of a common design space. The framework further exposes common design trade-offs across training objectives, inference algorithms, scaling behavior, systems optimization, and evaluation protocols, suggesting several promising directions for future research.
cs.LG↗
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Model (LLM) agents. However, most environments are scored only by game outcomes such as win rates and largely remain to text-only interaction, making it difficult to tell whether an agent's language is actually grounded in what it perceived and did, or to identify the failure modes underlying its behavior. To address this gap, we introduce QUACK, an open-source environment and evaluation framework for auditing the grounding of agent language in multimodal social reasoning. QUACK evaluates agents at three levels: game outcomes, behavioral trajectories, and utterance-level consistency. Its core Statement Verification Pipeline reconstructs each agent's ground-truth trajectory from engine logs and checks every discussion claim against it, automatically flagging spatial hallucination, unsupported accusation, deception collapse, and language-action inconsistency. Evaluating three frontier VLMs in both homogeneous and cross-model adversarial settings, we find that even the strongest agent hallucinates 15.1% of its verifiable spatial claims and 11.5% of accusations are strictly unsupported. We release the full engine, evaluation framework, toolkit, and logs in https://github.com/AAAAA-Academia-Attractions/QUACK.
cs.CL↗
Weighted Reverse Convolution for Feature Upsampling
Pre-trained vision foundation models (VFMs) provide strong semantic representations, yet their patch-level features are inherently coarse, limiting their effectiveness on tasks requiring fine-grained localization, dense prediction, and point-wise correspondence. In this work, we revisit feature upsampling for VFMs from the perspective of \textbf{\textit{inverse problem}} and propose Weighted Reverse Convolution (WRC), a spatially adaptive inverse operator for densifying high-level visual descriptors. Specifically, we formulate feature upsampling as a weighted Tikhonov-regularized least-squares problem, where spatially varying weights modulate both data fidelity and prior strength at each spatial location. This allows WRC to adapt the reconstruction to spatially varying feature characteristics, thereby preserving critical structures while mitigating over-smoothing. Moreover, WRC retains an efficient, fully differentiable closed-form FFT solution, making it a practical drop-in upsampling operator. Integrated into a lightweight self-supervised densification framework, WRC consistently improves dense feature quality across various downstream benchmarks, including segmentation, depth estimation, video object segmentation, object discovery, and keypoint correspondence, while maintaining high computational efficiency.
cs.CV↗
Herculean: An Agentic Benchmark for Financial Intelligence
As AI agents improve, the central question is no longer whether they can solve isolated well-defined financial tasks, but whether they can reliably carry out financial professional work. Existing financial benchmarks offer only a partial view of this ability, as they primarily evaluate static competencies such as question answering, retrieval, summarization, and classification. We introduce Herculean, the first skilled benchmark for agentic financial intelligence spanning four representative workflows, including Trading, Hedging, Market Insights, and Auditing. Each workflow is instantiated as a standardized MCP-based skill environment with its own tools, interaction dynamics, constraints, and success criteria, enabling consistent end-to-end assessment of heterogeneous agent systems. Across frontier agents, we find agents perform relatively well on Trading and Market Insights, but struggle substantially on Hedging and Auditing, where long-horizon coordination, state consistency, and structured verification are critical. Overall, our results point to a key gap in current agents in turning financial reasoning into dependable workflow execution in high-stakes financial workflows.
cs.AI↗
Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization
Large language models (LLMs) excel at general-purpose tasks, yet adapting their responses to individual users remains challenging. Retrieval augmentation provides a lightweight alternative to fine-tuning by conditioning LLMs on user history records, and existing approaches typically select these records based on semantic relevance. We argue that relevance serves as an unreliable proxy for utility: a record may be semantically similar to a query yet fail to improve generation quality or even degrade it due to redundancy or conflicting information. To bridge this gap, we propose PURPLE, a contextual bandit framework that oPtimizes UseR Profiles for LLM pErsonalization. In contrast to a greedy selection of the most relevant records, PURPLE treats profile construction as an order-sensitive generation process and utilizes a Plackett-Luce ranking model to capture complex inter-record dependencies. By training with semantically rich feedback provided by the likelihood of the reference response, our method aligns retrieval directly with generation quality. Extensive experiments on nine personalization tasks demonstrate that PURPLE consistently outperforms strong heuristic and retrieval-augmented baselines in both effectiveness and efficiency, establishing a principled and scalable solution for optimizing user profiles.
cs.CL↗
Analysing Knowledge Construction in Online Learning: Adapting the Interaction Analysis Model for Unstructured Large-Scale Discourse
The rapid expansion of online courses and social media has generated large volumes of unstructured learner-generated text. Understanding how learners construct knowledge in these spaces is crucial for analysing learning processes, informing content design, and providing feedback at scale. However, existing approaches typically rely on manual coding of well-structured discussion forums, which does not scale to the fragmented discourse found in online learning. This study proposes and validates a framework that combines a codebook inspired by the Interaction Analysis Model with an automated classifier to enable large-scale analysis of knowledge construction in unstructured online discourse. We adapt four comment-level categories of knowledge construction: Non-Knowledge Construction, Share, Explore, and Integrate. Three trained annotators coded a balanced sample of 20,000 comments from YouTube education channels. The codebook demonstrated strong reliability, with Cohen's kappa = 0.79 on the main dataset and 0.85--0.93 across four additional educational domains. For automated classification, bag-of-words baselines were compared with transformer-based language models using 10-fold cross-validation. A DeBERTa-v3-large model achieved the highest macro-averaged F1 score (0.841), outperforming all baselines and other transformer models. External validation on four domains yielded macro-F1 above 0.705, with stronger transfer in medicine and programming, where discourse was more structured and task-focused, and weaker transfer in language and music, where comments were more varied and context-dependent. Overall, the study shows that theory-driven, semi-automated analysis of knowledge construction at scale is feasible, enabling the integration of knowledge-construction indicators into learning analytics and the design of online learning environments.
cs.CL↗
Distinguishable-particle Glassy Crystal: the simplest molecular model of glass
The nature of glassy dynamics and the glass transition are long-standing problems under active debate. In the presence of a structural disorder widely believed to be an essential characteristic of structural glass, identifying and understanding key dynamical behaviors are very challenging. In this work, we demonstrate that an energetic disorder, which usually results from a structural disorder, is instead a more essential feature of glass. Specifically, we develop a distinguishable-particle glassy crystal (DPGC) in which particles are ordered in a face-centered cubic lattice and follow particle-dependent random interactions, leading to an energetic disorder in the particle configuration space. Molecular dynamics simulations in the presence of vacancy-induced particle diffusion show typical glassy behaviors. A unique feature of this molecular model is the knowledge of the complete set of inherent structures with easily calculable free energies, implying a well-understood potential energy landscape.
cond-mat.stat-mech↗
Demystifying Compiler Unstable Feature Usage and Impacts in the Rust Ecosystem
Rust programming language is gaining popularity rapidly in building reliable and secure systems due to its security guarantees and outstanding performance. To provide extra functionalities, the Rust compiler introduces Rust unstable features (RUF) to extend compiler functionality, syntax, and standard library support. However, these features are unstable and may get removed, introducing compilation failures to dependent packages. Even worse, their impacts propagate through transitive dependencies, causing large-scale failures in the whole ecosystem. Although RUF is widely used in Rust, previous research has primarily concentrated on Rust code safety, with the usage and impacts of RUF from the Rust compiler remaining unexplored. Therefore, we aim to bridge this gap by systematically analyzing the RUF usage and impacts in the Rust ecosystem. We propose novel techniques for extracting RUF precisely, and to assess its impact on the entire ecosystem quantitatively, we accurately resolve package dependencies. We have analyzed the whole Rust ecosystem with 590K package versions and 140M transitive dependencies. Our study shows that the Rust ecosystem uses 1000 different RUF, and at most 44% of package versions are affected by RUF, causing compiling failures for at most 12%. To mitigate wide RUF impacts, we further design and implement a RUF-compilation-failure recovery tool that can recover up to 90% of the failure. We believe our techniques, findings, and tools can help to stabilize the Rust compiler, ultimately enhancing the security and reliability of the Rust ecosystem.
cs.SE↗
Not all that is $\beta_0$ is $\beta$-function: the DGLAP resummation and the running coupling in NLO JIMWLK
We reanalyze the origin of the large transverse logarithms associated with the QCD one loop beta-function coefficient in the NLO JIMWLK Hamiltonian. We show that some of these terms are not associated with the running of the QCD coupling constant but rather with the DGLAP evolution. The DGLAP-like resummation of these logarithms is mandatory within the JIMWLK Hamiltonian, as long as the color correlation length in the projectile is larger than that in the target. This regime in fact covers the whole range of rapidities at which JIMWLK evolution is supposed to be applicable. We derive the RG equation that resums these logarithms to all orders in alpha_s in the JIMWLK Hamiltonian. This is a nonlinear equation for the eikonal scattering matrix S(x). We solve this equation and perform the DGLAP resummation in two simple cases: the dilute limit, where both the projectile and the target are far from saturation, and the saturated regime, where the target correlation length also determines its saturation momentum.
hep-ph↗
Fabrication of CeO2 by sol-gel process based on microfluidic technology as an analog preparation of ceramic nuclear fuel microspheres
Microfluidics integrated with sol-gel processes is introduced in preparing monodispersed MOX nuclear fuel microspheres using nonactive cerium as a surrogate for uranium or plutonium. The detailed information about microfluidic devices and sol-gel processes are provided. The effects of viscosity and flow rate of continuous and dispersed phase on size and size distribution of CeO2 microspheres have been investigated. A comprehensive characterization of the CeO2 microspheres has been conducted, including XRD pattern, SEM, density, size and size distribution. The size of prepared monodisperse particles can be controlled precisely in range of 10μm to 1000μm and the particle CV is below 3%.
nucl-ex↗